<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xlm-roberta-base-Mixed-swap
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2697
- Accuracy: 0.7988
- F1: 0.7988
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.7332 | 1.0 | 316 | 0.5436 | 0.7821 | 0.7638 |
0.4604 | 2.0 | 632 | 0.5950 | 0.7927 | 0.7702 |
0.3556 | 3.0 | 948 | 0.6198 | 0.7806 | 0.7834 |
0.2804 | 4.0 | 1264 | 0.8112 | 0.8018 | 0.7933 |
0.2325 | 5.0 | 1580 | 0.7812 | 0.7973 | 0.8015 |
0.1861 | 6.0 | 1896 | 1.0053 | 0.8003 | 0.8011 |
0.1544 | 7.0 | 2212 | 1.0666 | 0.7973 | 0.7949 |
0.1176 | 8.0 | 2528 | 1.1536 | 0.8109 | 0.8103 |
0.0929 | 9.0 | 2844 | 1.2417 | 0.7988 | 0.7975 |
0.078 | 10.0 | 3160 | 1.2697 | 0.7988 | 0.7988 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3